Search results

Sarcasm is a linguistic expression that usually carries the opposite meaning of what is being said by words, thus making it difficult for machines to discover the actual meaning. It is mainly distinguished by the inflection with which it is spoken, with an undercurrent of irony, and is largely dependent on context, which makes it a difficult task for computational analysis. Moreover, sarcasm expresses negative sentiments using positive words, allowing it to easily confuse sentiment analysis models. This paper aims to demonstrate the task of sarcasm detection using the approach of machine and deep learning.

For the purpose of sarcasm detection, machine and deep learning models were used on a data set consisting of 1.3 million social media comments, including both sarcastic and non-sarcastic comments. The data set was pre-processed using natural language processing methods, and additional features were extracted and analysed. Several machine learning models, including logistic regression, ridge regression, linear support vector and support vector machines, along with two deep learning models based on bidirectional long short-term memory and one bidirectional encoder representations from transformers (BERT)-based model, were implemented, evaluated and compared.

The performance of machine and deep learning models was compared in the task of sarcasm detection, and possible ways of improvement were discussed. Deep learning models showed more promise, performance-wise, for this type of task. Specifically, a state-of-the-art model in natural language processing, namely, BERT-based model, outperformed other machine and deep learning models.

This study compared the performance of the various machine and deep learning models in the task of sarcasm detection using the data set of 1.3 million comments from social media.

The Overall Equipment Effectiveness (OEE) is considered a standard for measuring equipment productivity in terms of efficiency. Still, Artificial Intelligence solutions are rarely used for analyzing OEE results and identifying corrective actions. Therefore, the approach proposed in this paper aims to provide a new rule-based Machine Learning (ML) framework for OEE enhancement and the selection of improvement actions.

Association Rules (ARs) are used as a rule-based ML method for extracting knowledge from huge data. First, the dominant loss class is identified and traditional methodologies are used with ARs for anomaly classification and prioritization. Once selected priority anomalies, a detailed analysis is conducted to investigate their influence on the OEE loss factors using ARs and Network Analysis (NA). Then, a Deming Cycle is used as a roadmap for applying the proposed methodology, testing and implementing proactive actions by monitoring the OEE variation.

The method proposed in this work has also been tested in an automotive company for framework validation and impact measuring. In particular, results highlighted that the rule-based ML methodology for OEE improvement addressed seven anomalies within a year through appropriate proactive actions: on average, each action has ensured an OEE gain of 5.4%.

The originality is related to the dual application of association rules in two different ways for extracting knowledge from the overall OEE. In particular, the co-occurrences of priority anomalies and their impact on asset Availability, Performance and Quality are investigated.

This paper focuses on image-to-text manuscript processing through Handwritten Text Recognition (HTR), a Machine Learning (ML) approach enabled by Artificial Intelligence (AI). With HTR now achieving high levels of accuracy, we consider its potential impact on our near-future information environment and knowledge of the past.

In undertaking a more constructivist analysis, we identified gaps in the current literature through a Grounded Theory Method (GTM). This guided an iterative process of concept mapping through writing sprints in workshop settings. We identified, explored and confirmed themes through group discussion and a further interrogation of relevant literature, until reaching saturation.

Catalogued as part of our GTM, 120 published texts underpin this paper. We found that HTR facilitates accurate transcription and dataset cleaning, while facilitating access to a variety of historical material. HTR contributes to a virtuous cycle of dataset production and can inform the development of online cataloguing. However, current limitations include dependency on digitisation pipelines, potential archival history omission and entrenchment of bias. We also cite near-future HTR considerations. These include encouraging open access, integrating advanced AI processes and metadata extraction; legal and moral issues surrounding copyright and data ethics; crediting individuals’ transcription contributions and HTR’s environmental costs.

Our research produces a set of best practice recommendations for researchers, data providers and memory institutions, surrounding HTR use. This forms an initial, though not comprehensive, blueprint for directing future HTR research. In pursuing this, the narrative that HTR’s speed and efficiency will simply transform scholarship in archives is deconstructed.

This study aims to review recent advances towards the implementation of ANN and NLP applications during the budgeting phase of the construction process. During this phase, construction companies must assess the scope of each task and map the client’s expectations to an internal database of tasks, resources and costs. Quantity surveyors carry out this assessment manually with little to no computer aid, within very austere time constraints, even though these results determine the company’s bid quality and are contractually binding.

This paper seeks to compile applications of machine learning (ML) and natural language processing in the architectural engineering and construction sector to find which methodologies can assist this assessment. The paper carries out a systematic literature review, following the preferred reporting items for systematic reviews and meta-analyses guidelines, to survey the main scientific contributions within the topic of text classification (TC) for budgeting in construction.

This work concludes that it is necessary to develop data sets that represent the variety of tasks in construction, achieve higher accuracy algorithms, widen the scope of their application and reduce the need for expert validation of the results. Although full automation is not within reach in the short term, TC algorithms can provide helpful support tools.

Given the increasing interest in ML for construction and recent developments, the findings disclosed in this paper contribute to the body of knowledge, provide a more automated perspective on budgeting in construction and break ground for further implementation of text-based ML in budgeting for construction.

Political Corporate Social Responsibility (CSR), based on ideas about deliberative democracy, have been criticised for increasing corporate power and democratic deficits. Yet, deliberative ideals are flourishing in the corporate world in the form of dialogues with a broad set of stakeholders and engagement in wider societal issues. Extractive industry areas, with extensive corporate interventions in weak regulatory environments, are particularly vulnerable to asymmetrical power relations when businesses engage with society. This paper aims to illustrate in what way deliberative CSR practices in such contexts risk enhancing corporate power at the expense of community interests.

This paper is based on a retrospective qualitative study of a Canadian oil company, operating in an Albanian oilfield between 2009 and 2016. Through a study of three different deliberative CSR practices – market-based land acquisition, a grievance redress mechanism and dialogue groups – it highlights how these practices in various ways enforced corporate interests and prevented further community mobilisation.

By applying Laclau and Mouffe’s theory of hegemony, the analysis highlights how deliberative CSR activities isolated and silenced community demands, moved some community members into the corporate alliance and prevented alternative visions of the area to be articulated. In particular, the close connection between deliberative practices and monetary compensation flows is underlined in this dynamic.

The paper contributes to critical scholarship on political CSR by highlighting in what way deliberative practices, linked to monetary compensation schemes, enforce corporate hegemony by moving community members over to the corporate alliance.

This study aims to ensure reliable analysis of dynamic responses in asphalt pavement structures. It investigates noise reduction and data mining techniques for pavement dynamic response signals.

The paper conducts time-frequency analysis on signals of pavement dynamic response initially. It also uses two common noise reduction methods, namely, low-pass filtering and wavelet decomposition reconstruction, to evaluate their effectiveness in reducing noise in these signals. Furthermore, as these signals are generated in response to vehicle loading, they contain a substantial amount of data and are prone to environmental interference, potentially resulting in outliers. Hence, it becomes crucial to extract dynamic strain response features (e.g. peaks and peak intervals) in real-time and efficiently.

The study introduces an improved density-based spatial clustering of applications with Noise (DBSCAN) algorithm for identifying outliers in denoised data. The results demonstrate that low-pass filtering is highly effective in reducing noise in pavement dynamic response signals within specified frequency ranges. The improved DBSCAN algorithm effectively identifies outliers in these signals through testing. Furthermore, the peak detection process, using the enhanced findpeaks function, consistently achieves excellent performance in identifying peak values, even when complex multi-axle heavy-duty truck strain signals are present.

The authors identified a suitable frequency domain range for low-pass filtering in asphalt road dynamic response signals, revealing minimal amplitude loss and effective strain information reflection between road layers. Furthermore, the authors introduced the DBSCAN-based anomaly data detection method and enhancements to the Matlab findpeaks function, enabling the detection of anomalies in road sensor data and automated peak identification.

The study seeks to understand the possible opportunities that Industry 5.0 might offer for various aspects of inclusive sustainability. The study aims to discuss existing perspectives on the classification of Industry 5.0 technologies and their underlying role in materializing the sustainability values of this agenda.

The study systematically reviewed Industry 5.0 literature based on the PRISMA protocol. The study further employed a detailed content-centric review of eligible documents and conducted evidence mapping to fulfill the research objectives.

The advancement of Industry 5.0 is currently underway, with noteworthy initial contributions enriching its knowledge base. Although a unanimous definition remains lacking, diverse viewpoints emerge concerning the recognition of fundamental technologies and the potential for yielding sustainable outcomes. The expected contribution of Industry 5.0 to sustainability varies significantly depending on the context and the nature of underlying technologies.

Industry 5.0 holds the potential for advancing sustainability at both the firm and supply chain levels. It is envisioned to contribute proportionately to the three sustainability dimensions. However, the current discourse primarily dwells in theoretical and conceptual domains, lacking empirical exploration of its practical implications.

This study comprehensively explores diverse perspectives on Industry 5.0 technologies and their potential contributions to economic, environmental and social sustainability. Despite its promise, the practical evidence supporting the effectiveness of Industry 5.0 remains limited. Certain conditions are necessary to realize the benefits of Industry 5.0 fully, yet the mechanisms behind these conditions require further investigation. In this regard, the study suggests several potential areas for future research.

This study aims to answer the question of how to structure a circular ecosystem for extractive fishing in the Amazon region. It explores possibilities for implementing a circular ecosystem management model in an imperfect market with low technological availability, high informality and limited public assistance.

Qualitative approach was adopted for this paper, with a case study on extractive fishing in the state of Amazonas. Data was collected through 35 interviews and direct observation of the processes of collecting, storing and transporting fish on two routes: Tapauá-Manaus and Manacapuru-Manaus.

Through the data collected, it was possible to observe the importance of an orchestrating agent – such as an association or even a public authority – for the establishment and development of a circular ecosystem for extractive fishing in the region.

The paper makes theoretical contributions by presenting how a circular ecosystem management model could be implemented for an imperfect market in the Global South, as well as contributing to the literature on how the circular economy contributes to mitigate the threat to biodiversity posed by the linear economy.

It contributes to the management practice of structuring circular ecosystems.

The role of public authorities and the collective organization of fishermen as orchestrators connecting the network of actors that develop the extractive fishing ecosystem is fundamental, guaranteeing effective social participation in solving local problems.

The idea of circular ecosystems was applied to imperfect contexts, with high informality, weak institutions and bioeconomy, topics still little explored in the literature.

In response to growing concerns over the negative consequences of Internet addiction on adolescents’ mental health, coupled with conflicting results in this literature stream, this meta-analysis sought to (1) examine the association between Internet addiction and depressive symptoms in adolescents, (2) examine the moderating role of Internet freedom across countries, and (3) examine the mediating role of excessive daytime sleepiness.

In total, 52 studies were analyzed using robust variance estimation and meta-analytic structural equation modeling.

There was a significant and moderate association between Internet addiction and depressive symptoms. Furthermore, Internet freedom did not explain heterogeneity in this literature stream before and after controlling for study quality and the percentage of female participants. In support of the displacement hypothesis, this study found that Internet addiction contributes to depressive symptoms through excessive daytime sleepiness (proportion mediated = 17.48%). As the evidence suggests, excessive daytime sleepiness displaces a host of activities beneficial for maintaining mental health. The results were subjected to a battery of robustness checks and the conclusions remain unchanged.

The results underscore the negative consequences of Internet addiction in adolescents. Addressing this issue would involve interventions that promote sleep hygiene and greater offline engagement with peers to alleviate depressive symptoms.

This study utilizes robust meta-analytic techniques to provide the most comprehensive examination of the association between Internet addiction and depressive symptoms in adolescents. The implications intersect with the shared interests of social scientists, health practitioners, and policy makers.

The purpose of this study is to identify and synthesise the best evidence on health-care leaders’ and professionals’ experiences and perceptions of compassionate leadership.

A mixed-methods systematic review was conducted in accordance with the Joanna Briggs Institute methodology for mixed-methods systematic reviews using a convergent integrated approach. A systematic search was done in January 2023 in PubMed, CINAHL, Scopus, Medic and MedNar databases. The results were reported based on Preferred Reporting Items for Systematic Reviews and Meta-analyses. The data was analysed using thematic analysis.

Ten studies were included in the review (five qualitative and five quantitative). The thematic analysis identified seven analytical themes as follows: treating professionals as individuals with an empathetic and understanding approach; building a culture for open and safe communication; being there for professionals; giving all-encompassing support; showing the way as a leader and as a strong professional; building circumstances for efficient work and better well-being; and growing into a compassionate leader.

Compassionate leadership can possibly address human resource-related challenges, such as health-care professionals’ burnout, turnover and the lack of patient safety. It should be taken into consideration by health-care leaders, their education and health-care organisations when developing their effectiveness.

This review synthesised the knowledge of compassionate leadership in health care and its benefits by providing seven core elements of health-care leaders’ and professionals’ experiences and perceptions of compassionate leadership.